Graduate Council

SUPPORTING MATERIAL

Minor in High Performance Computing

I. New Minor in High Performance Computing

A. *The objectives of the program: an explanation of how the proposal meets the new educational objectives and/or strengthens existing programs of the college(s) and the University and what students may expect to accomplish through the program.*

The **objectives** of the new minor are to educate graduate students in scientific and high performance computing with an emphasis on the capabilities and uses of parallel computers.

**Background** - For United States industry to remain competitive in the global marketplace it must update its approaches to product development. At the same time, advances in basic science have become heavily dependent on simulations performed on high performance computers. Such simulations are at the leading edge of scientific computing and many problems remain beyond the capabilities of current computing capabilities. Such needs have resulted in the High Performance Computing and Communications (HPCC) program: a multi-agency government effort to advance the scientific computing capabilities of the United States by a factor of 1000 by the end of the present decade. The achievement of "scaled teraFLOP performance" must rely on parallel computer architectures. The United States is no longer the leader in vector computing; the Japanese have at least drawn even. The conversion of supercomputing from sequential/vector to parallel is crucial as that is where the United States still leads. However, this lead has been jeopardized by our failure to get parallel machines and parallel software technology into the hands of users. Thus, the education of our university students in the capabilities and uses of advanced parallel computers is an essential component in the United States competitive industrial edge as well as our continued leadership in fundamental scientific research.

In recognition of this need, faculty in the Colleges of Engineering, Science, and Earth and Mineral Sciences combined in 1995 to propose to the National Science Foundation to develop a curriculum in high performance computing that emphasizes the application of advanced computing to the solution of problems of practical importance in science and engineering. This proposal was funded by the National Science Foundation under its Combined Research Curriculum Development Program. As part of this program it was proposed to develop new courses at the senior undergraduate and graduate levels and to introduce a new graduate minor in high performance computation. The proposed courses have now been developed and taught, at least once, as discussed below.

Recently, Penn State's College of Engineering established an interdisciplinary institute to promote the use of the fastest and most advanced computers in education and research. Called the "Institute for High Performance Computing Applications", the organization was established in consultation and cooperation with the colleges of science and earth and mineral sciences, the Center for Academic Computing and the Applied Research Laboratory. The Institute has both a research and instructional mission. The proposed minor in high performance computation is part of its instructional activities.

For more information, access the Institute Homepage on the World Wide Web at URL http://www.psu.edu/dept/ihpca/

- The following courses are being added to the regularly listed courses offered yearly or biyearly at Penn State. These courses have already been taught at least once under the temporary course numbers. These courses form part of the core of the graduate minor. One existing course forms the balance of the core as described below. Copies of course outlines for the two new courses are attached as Appendix B. Appendix B also includes the course outline for the existing core course.

AERSP 424: Introduction to Parallel Computing for Engineers.

NUC E 530: Parallel/Vector Algorithms for Scientific Applications

In addition a 1-credit graduate seminar in high performance computing is being offered twice a year. It is planned to request a permanent course number for both seminars. At present they are offered under the following designation:

AERSP/MATH/CSE 597E: Seminar in High Performance Computing Applications

C: Complete Program Statement

GRADUATE MINOR IN HIGH PERFORMANCE COMPUTATION

Professor Philip J. Morris, in charge

The Executive Committee of the Institute for High Performance Computing Applications (IHPCA) will administer this interdisciplinary minor. Each student’s program will be planned by the student and a designated IHPCA advisor, in consultation with the graduate advisor in the student’s major field.

The minor offers an opportunity for students in all colleges and majors to pursue a focused set of courses that emphasize the use of high performance computers to solve problems in science and engineering.

The minor requires 9 credits in high performance computing courses for a masters’ and 15 credits for a doctoral minor. Six credits will be taken from

AERSP 424: Introduction to Parallel Computing for Engineers

CSE 530: Computer Architecture

NUC E 530: Parallel/Vector Algorithms for Scientific Applications

In addition, students selecting the minor are encouraged to register for one or both of the high performance computing seminars offered in the Fall and Spring semesters.

Each of the core courses will be offered once every year. On addition, the course prerequisites can be met readily by students in science and engineering. For example, AERSP 424 only requires basic calculus and programming courses. NUC E 530 has AERSP 424 as a possible prerequisite and the instructors for CSE 530 and AERSP 424 have agreed to collaborate to make sure that AERSP 424 is an acceptable prerequisite for CSE 530. The situation for students with a non-science background will be considered on a case by case basis.

The remaining credits required for the minor will include 400- and 500-level high performance computing courses from the list below.

ACS 597: Computational acoustics

AERSP 424: Introduction to parallel computing for engineers

AERSP 529: Advanced analysis and computation of turbomachinery flows

AERSP 597: Aerodynamic shape design

CHE 597: Numerical methods in chemical engineering

CHEM 560: Quantum mechanical electronic structure calculations

CHEM 560: Molecular Dynamics / Monte Carlo Methods for Physical Scientists

CSE 530: Computer architecture

CSE 531: Parallel processors and processing

CSE 532: Multiprocessor architecture

CSE 543: Interconnection networks in highly parallel computers

EE 537: Numerical and asymptotic methods in electromagnetics

EMCH 560: Finite element methods

EMCH 562/ABE 562: Boundary element analysis

EMCH 563/ME 563: Nonlinear finite element methods

IE 578: Using simulation models for design

MATH/CSE 550: Numerical linear algebra

MATH/CSE 551: Numerical solution of ordinary differential equations

MATH/CSE 552: Numerical solution of partial differential equations

MATH/CSE 555: Numerical optimization techniques

MATH/CSE 556: Finite element methods

ME/AERSP 526: Computational methods for shear layers

ME/AERSP 527: Computational methods in transonic flow

ME/AERSP 528: Computational methods for recirculating flows

ME 540: Numerical solutions applied to heat transfer and fluid mechanics

METEO 526: Numerical weather prediction

METEO 586: Advances in numerical weather prediction

NUC E 530: Parallel/Vector Algorithms for Scientific Applications

PHYS 527: Computational physics

It is anticipated that each of these courses will be offered at least once during a two-year cycle. The Executive Committee of the Institute for High Performance Computing Applications may add additional to this list following review.

D: A justification for the program:

As discussed in the introductory material, high performance computing enters all areas of research and is an essential ingredient in the continued leadership of United States scientific and engineering leadership. It also enters everyone’s lives through the use of high performance computing in business and entertainment. The Institute for High Performance Computing Applications has a mission to promote excellence in research and education in this area.

The provision of a graduate minor in high performance computation will:

1. Provide courses to graduate students in all colleges and majors in the application of high performance computing to the solution of problems of both scientific and engineering importance.

2. Provide a degree of external visibility that is crucial to the recruitment of high quality students and faculty.

3. Promote interdisciplinary research and instruction.

The Institute for High Performance Computing Applications is located administratively in the Department of Aerospace Engineering. Associated faculty are located in the colleges of engineering, earth and mineral sciences, liberal arts, and science.

E: Other departments and programs with significant relationships to high performance computing have been consulted about the proposed graduate minor, and supporting statements from the appropriate units are included with this submission in Appendix A. These departments are listed here:

Graduate Program in Acoustics

Aerospace Engineering

Agricultural & Biological Engineering

Architectural Engineering

Chemistry

Civil and Environmental Engineering

Computer Science & Engineering

Electrical Engineering

Engineering Science & Mechanics

Geosciences

Industrial & Manufacturing Engineering

Mathematics

Mechanical Engineering

Meteorology

Nuclear Engineering

Physics